Search

Mobile applications have become a commodity in multiple daily scenarios. Their increasing complexity has led mobile software ecosystems to become heterogeneous in terms of hardware specifications, features and context of use, among others. For their users, fully exploiting their potential has become challenging. While enacting software systems with adaptation mechanisms has proven to ease this burden from users, mobile devices present specific challenges related to privacy and security concerns. Nevertheless, rather than being a limitation, users can play a proactive role in the adaptation loop by providing valuable feedback for runtime adaptation. To this end, we propose the use of chatbots to interact with users through a human-like smart conversational process. We depict a work-in-progress proposal of an end-to-end framework to integrate semi-automatic adaptation mechanisms for mobile applications. These mechanisms include the integration of both implicit and explicit user feedback for autonomous user categorization and execution of enactment action plans. We illustrate the applicability of such techniques through a set of scenarios from the Mozilla mobile applications suite. We envisage that our proposal will improve user experience by bridging the gap between users’ needs and the capabilities of their mobile devices through an intuitive and minimally invasive conversational mechanism. This work has been partially supported by AGAUR, code 2017-SGR-1694. The corresponding author gratefully acknowledges the Universitat Politècnica de Catalunya and Banco Santander for the financial support of his predoctoral grant FPI-UPC.

Path finding for autonomous agents has been traditionally driven by finding optimal paths, typically by using A* search or any of its variants. When it comes to simulating virtual humanoids, traditional approaches rarely consider aspects of human memory or orientation. In this work, we propose a new path finding algorithm, inspired by current research regarding how the brain learns and builds cognitive maps. Our method represents the space as a hexagonal grid with counters, based on brain research that has investigated how memory cells are fired. Our path finder then combines a method for exploring unknown environments while building such a cognitive map, with an A* search using a modified heuristic that takes into account the cognitive map. The resulting paths show how as the agent learns the environment, the paths become shorter and more consistent with the optimal A* search. Moreover, we run a perceptual study to demonstrate that the viewers could successfully identify the intended level of knowledge of the simulated agents. This line of research could enhance the believability of autonomous agents’ path finding in video games and other VR applications. This work was partly funded by the Spanish Ministry of Economy, Industry and Competitiveness under Grant No. TIN2017- 88515-C2-1-R.

Digital/electronic identities are essential components of collaborative robots/robots and human-robot/robothuman interactions. Through such identities, digital agents (AI powered software or robots/bots) are entrusted with tasks in the name of certain individuals/companies. Digital identities can come from various sources; these can be assigned by an employer, through a service provided by a government entity or an external company specializing in the creation of such signatures or generated through an interface like Facebook Connect. All these different sources offer a range of varying levels of trust, both within the institution where the signature is principally used, but especially when interacting with third parties. Ultimately, this level of trust or its valuation is a determining factor in how far the authorization of the respective digital/electronic signature goes. The authors describe the application of digital/electronic signatures from human employees or legal entities which, simultaneously with the main task, generate sub-signatures for the respective digital agent.The topic is presented from a technical perspective as well as from a social science point of view., peer-reviewed

The growing need of technological assistance to provide support to people with special needs demands for systems more and more efficient and with better performances. With this aim, this work tries to advance in a multirobot platform that allows the coordinated control of different agents and other elements in the environment to achieve an autonomous behavior based on the user’s needs or will. Therefore, this environment is structured according to the potentiality of each agent and elements of this environment and of the dynamic context, to generate the adequate actuation plans and the coordination of their execution.

This study used diaries and interviews to examine everyday information seeking behaviors among a group of frequent users of intelligent personal assistants. All participants completed diaries and met for a brief interview following the completion of their diaries. Diary responses captured real life examples of intelligent personal assistant usage, while interviews focused on general perceptions of intelligent personal assistants. Participants frequently used their intelligent personal assistants to find factual information but often expressed reluctance to ask assistants questions that would be difficult for the assistants to answer well. Many assistant uses were for repetitive and frequent types of information needs. Participants expressed mixed opinions about the appropriateness of intelligent personal assistant use in social situations. Some, though not all, of the findings of this study confirm the findings of other research in the growing body of research on intelligent personal assistants.

In recent years, an increasing number of Mixed Reality (MR) applications have been developed using agent technology—both for the underlying software and as an interface metaphor. However, no unifying field or theory currently exists that can act as a common frame of reference for these varied works. As a result, much duplication of research is evidenced in the literature. This paper seeks to fill this important gap by outlining ‘‘for the first time’’ a formal field of research that has hitherto gone unacknowledged, namely the field of Mixed Reality Agents (MiRAs), which are defined as agents embodied in a Mixed Reality environment. Based on this definition, a taxonomy is offered that classifies MiRAs along three axes: agency, based on the weak and strong notions outlined by Wooldridge and Jennings (1995); corporeal presence, which describes the degree of virtual or physical representation (body) of a MiRA; and interactive capacity, which characterises its ability to sense and act on the virtual and physical environment. Furthermore, this paper offers the first comprehensive survey of the state-of-the-art of MiRA research and places each project within the proposed taxonomy. Finally, common trends and future directions for MiRA research are discussed. By defining Mixed Reality Agents as a formal field, establishing a common taxonomy, and retrospectively placing existing MiRA projects within it, future researchers can effectively position their research within this landscape, thereby avoiding duplication and fostering reuse and interoperability. Science Foundation Ireland au,ti,ke,SB-09/09/2011

Traditionally, social interaction research has concentrated on either fully virtually embodied agents (e.g. embodied conversational agents) or fully physically embodied agents (e.g. robots). For some time, however, both areas have started augmenting their agents’ capabilities for social interaction using ubiquitous and intelligent environments. We are placing different agent systems for social interaction along Milgram’s Reality-Virtuality Continuum—according to the degree they are embodied in a physical, virtual or mixed reality environment—and show systems that follow the next logical step in this progression, namely social interaction in the middle of Milgram’s continuum, that is, agents richly embodied in the physical and virtual world. This paper surveys the field of social interaction research with embodied agents with a particular view towards their embodiment forms and highlights some of the advantages and issues associated with the very recent field of social interaction with mixed reality agents. Science Foundation Ireland

Η παρούσα διπλωματική εργασία επιχειρεί τη δημιουργία ευφυών εικονικών πρακτόρων με συναισθηματική συμπεριφορά. Η ενσωμάτωση συναισθημάτων σε εφαρμογές εικονικής πραγματικότητας είναι απαραίτητη εάν επιθυμείται προσομοίωση της ανθρώπινης συμπεριφοράς, καθώς οι αποφάσεις και ενέργειες των ανθρώπων επηρεάζονται σε μεγάλο βαθμό από τη συναισθηματική τους κατάσταση. Αρχικά γίνεται μια ανασκόπηση των υπολογιστικών θεωριών και μοντέλων συναισθημάτων, τα οποία ήρθαν να αντικαταστήσουν τις παραδοσιακές θεωρίες συναισθημάτων, καθώς είναι κατάλληλα για υπολογιστικές εφαρμογές. Στη συνέχεια ακολουθεί ανάλυση των βασικών συστατικών του μοντέλου ALMA, το οποίο επιλέχθηκε μεταξύ των διαφόρων υπολογιστικών μοντέλων ως το καταλληλότερο για να εφαρμοστεί στην παρούσα εργασία. Στην ίδια ενότητα παρουσιάζονται κάποιες σημαντικές σχεδιαστικές αποφάσεις οι οποίες ήταν απαραίτητο να ληφθούν ώστε να καλύψουν τα αδιευκρίνιστά και μη δημοσιευμένα σημεία του μοντέλου ALMA, καθώς και των διαφόρων συναισθηματικών θεωριών που λαμβάνουν μέρος στον υπολογισμό των συναισθημάτων, διαθέσεων και προσωπικότητας. Η συγκεκριμένη ενότητα κλείνει με την παρουσίαση του μηχανισμού παραγωγής συναισθημάτων, μεταβολής διαθέσεων και επιλογής ενεργειών που προέκυψε από το συνδυασμό του μοντέλου ALMA και των σημαντικών σχεδιαστικών αποφάσεων που ελήφθησαν. Στη συνέχεια περιγράφεται αναλυτικά ο τρόπος με τον οποίο έγινε η υλοποίηση του μηχανισμού παραγωγής συναισθημάτων, μεταβολής διαθέσεων και επιλογής ενεργειών στην πλατφόρμα REVE Worlds. Στην ενότητα «Γραφική Απεικόνιση» παρουσιάζονται οι προσθήκες που έγιναν στην πλατφόρμα REVE Worlds, ώστε να υποστηρίζει την οπτικοποίηση συναισθημάτων, διαθέσεων, προσωπικότητας, ομιλίας και ενεργειών. Τέλος, παρουσιάζεται το ενδεικτικό σενάριο που υλοποιήθηκε, συνοδευόμενο από χαρακτηριστικά παραδείγματα εκτέλεσης. Η εργασία κλείνει με την εξαγωγή συμπερασμάτων και προτάσεων βελτίωσης της υλοποίησης., The current thesis is an attempt to create intelligent virtual agents with emotion-driven behavior. Integrating emotions on virtual reality applications is necessary in order to succeed human behavior simulation, as humans’ decisions and actions are greatly affected by their emotional state. The thesis begins by presenting an overview of the computational models and theories of emotion, which were developed in order to replace traditional emotion theories, as they are suitable for computational applications. The ALMA model was selected as the most appropriate for the current implementation, so a short presentation of its basic elements follows next. In the same unit the important implementation decisions are presented, which were taken in order to cover the obscure and unpublished spots of ALMA model, and of the diverse emotional theories which compute emotions, mood and personality. The specific unit ends by presenting the emotion creation, mood change and action selection mechanism that emerged by the combination of ALMA model and the important implementation decisions taken. To continue, the implementation of the emotion creation, mood change and action selection mechanism on REVE Worlds platform is described in detail. “Graphical Display” unit presents the extensions made on REVE Worlds platform in order to support emotions, mood, personality, speech and action display. Finally, the indicative implemented scenario is presented, followed by some characteristic execution examples. The thesis comes to an end by concluding and proposing ways of improving implementation

Enabling intuitive interaction in system design remains an art more than a science. This difficulty is exacerbated when the diversity of device and end user group is considered. In this paper, it is argued that conventional interaction modalities are unsuitable in many circumstances and that alternative modalities need be considered. Specifically the case of implicit interaction is considered, and the paper discusses how its use may lead to more satisfactory experiences. Specifically, harnessing implicit interaction in conjunction with the traditional explicit interaction modality, can enable a more intuitive and natural interactive experience. However, the exercise of capturing and interpreting implicit interaction is problematic and is one that lends itself to the adoption of AI techniques. In this position paper, the potential of lightweight intelligent agents is proposed as a model for harmonising the explicit and implicit components of an arbitrary interaction. Science Foundation Ireland 12M embargo until January 2012 - AV 10/05/2011

Emotions are crucial for user's decision making in recommendation processes. We first introduce ambient recommender systems, which arise from the analysis of new trends on the exploitation of the emotional context in the next generation of recommender systems. We then explain some results of these new trends in real-world applications through the smart prediction assistant (SPA) platform in an intelligent learning guide with more than three million users. While most approaches to recommending have focused on algorithm performance. SPA makes recommendations to users on the basis of emotional information acquired in an incremental way. This article provides a cross-disciplinary perspective to achieve this goal in such recommender systems through a SPA platform. The methodology applied in SPA is the result of a bunch of technology transfer projects for large real-world rccommender systems.

We present ACACIA, an agent-based program implemented in Java StarLogo 2.0 that simulates a two-dimensional microworld populated by agents, obstacles and goals. Our program simulates how agents can reach long-term goals by following sensorial-motor couplings (SMCs) that control how the agents interact with their environment and other agents through a process of local categorization. Thus, while acting in accordance with this set of SMCs, the agents reach their goals through the emergence of global behaviors. This agent-based simulation program would allow us to understand some psychological processes such as planning behavior from the point of view that the complexity of these processes is the result of agent-environment interaction.

Our work is focused on alleviating the workload for designers of adaptive courses on the complexity task of authoring adaptive learning designs adjusted to specific user characteristics and the user context. We propose an adaptation platform that consists in a set of intelligent agents where each agent carries out an independent adaptation task. The agents apply machine learning techniques to support the user modelling for the adaptation process.

This paper shows the impact of the atomic capabilities concept to include control-oriented knowledge of linear control systems in the decisions making structure of physical agents. These agents operate in a real environment managing physical objects (e.g. their physical bodies) in coordinated tasks. This approach is presented using an introspective reasoning approach and control theory based on the specific tasks of passing a ball and executing the offside manoeuvre between physical agents in the robotic soccer testbed. Experimental results and conclusions are presented, emphasising the advantages of our approach that improve the multi-agent performance in cooperative systems.

Τα εικονικά περιβάλλοντα είναι μια διαρκώς αναπτυσσόμενη περιοχή με πολλές και ενδιαφέρουσες εφαρμογές σε διάφορους τομείς, όπως η εκπαίδευση, η διασκέδαση και η προσομοίωση. Ένα σημαντικό τμήμα των εικονικών περιβαλλόντων που ενισχύει την αυτονομία και την αλληλεπιδραστικότητά τους είναι οι εικονικοί πράκτορες, δηλαδή οι αυτόνομες οντότητες του περιβάλλοντος που είναι σε θέση να αντιλαμβάνονται τον κόσμο γύρω τους και να εκτελούν ενέργειες ώστε να επιτύχουν τους στόχους τους. Οι εικονικοί πράκτορες χωρίζονται σε φυσικούς και γνωσιακούς. Στους πρώτoυς δίνεται έμφαση στην κίνηση και αλληλεπίδρασή τους με τα αντικείμενα του περιβάλλοντος, ενώ στους δεύτερους σε περισσότερο νοητικές ικανότητες, όπως η δυνατότητα μάθησης, επικοινωνίας, εξαγωγής συμπερασμάτων, κλπ. Κατά συνέπεια, οι φυσικοί πράκτορες αξιοποιούν κυρίως την έρευνα στους χώρους της ρομποτικής, συνθετικής κίνησης και μοντελοποίησης φυσικών νόμων, ενώ οι γνωσιακοί στηρίζονται σε αρχιτεκτονικές ευφυών πρακτόρων από τον χώρο της τεχνητής νοημοσύνης. Ένα βασικό μειονέκτημα της τρέχουσας έρευνας στους εικονικούς πράκτορες είναι η έλλειψη γενικών εργαλείων ανάπτυξης τέτοιων οντοτήτων, καθώς οι υπάρχουσες μηχανές τρισδιάστατων γραφικών φαίνεται να παρουσιάζουν σημαντικές ελλείψεις σε ό,τι αφορά τη λειτουργικότητα των πρακτόρων. Το πρόβλημα αυτό εντείνεται ακόμη περισσότερο με την απουσία κοινών μεθοδολογιών και αρχιτεκτονικών για τον σχεδίασμά και την ανάπτυξη εικονικών πρακτόρων, γεγονός που καθιστά δύσκολη την σύγκριση μεταξύ διαφορετικών προσεγγίσεων, αλλά και την άμεση επαναχρησιμοποίηση τμημάτων κώδικα της υπάρχουσας έρευνας. Τέλος, ένα ακόμη θεμελιώδες πρόβλημα που εμφανίζεται στην περιοχή των εικονικών πρακτόρων είναι η δυσκολία διασύνδεσης μεταξύ φυσικών και γνωσιακών ικανοτήτων ενός εικονικού πράκτορα, λόγω του διαφορετικού επιπέδου αφαίρεσης στον τρόπο αναπαράστασης της γνώσης στις δύο αυτές περιοχές. Τα παραπάνω προβλήματα αποτελούν το αντικείμενο μελέτης της τρέχουσας διατριβής, που έχει ως θέμα την εισαγωγή ευφυών πρακτόρων σε εικονικά περιβάλλοντα, δηλαδή τη δυνατότητα σχεδιασμού και ανάπτυξης τρισδιάστατων συνθετικών χαρακτήρων με ενισχυμένα γνωσιακά χαρακτηριστικά.

In this paper, we present the SHARE-it approach to the integration of agent technology with other existing technologies to build specific intelligent and semi-autonomous assistive devices for older persons and people with disabilities (both cognitive and/or motor). In particular, we explored the benefits of the concept of situated intelligence to build mobility platforms and other artefacts that enhance the autonomy of the target user group in their daily life so that they can be self-dependent enough to autonomously live in their preferred environment.

Περίληψη: Μη διαθέσιμο

In the context of Assistive Technologies, the present work addresses the improvement and greater adaptability of iTutorials, a supportive system which is intended to provide in-home support to cognitively impaired older adults in the performance of Activities of Daily Living.